Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly question marks and full stops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Among those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Referanser
    -0.45
    MessageWindow
    -0.41
    ghijklmnop
    -0.40
    sätzlich
    -0.40
    ymce
    -0.39
    MENAFN
    -0.39
    boutin
    -0.37
    schrank
    -0.36
     felon
    -0.36
    rabaya
    -0.35
    POSITIVE LOGITS
     propOrder
    0.52
    zerű
    0.50
    ьаж
    0.49
     незавершена
    0.47
    SourceChecksum
    0.47
    كويكب
    0.45
    ByVersion
    0.45
     ویکی‌پدی
    0.44
    tahui
    0.44
    Assuming
    0.44
    Act Density 0.008%

    No Known Activations